A survey of deep learning techniques for neural machine translation
In recent years, natural language processing (NLP) has got great development with deep
learning techniques. In the sub-field of machine translation, a new approach named Neural …
learning techniques. In the sub-field of machine translation, a new approach named Neural …
Towards robust neural machine translation
Small perturbations in the input can severely distort intermediate representations and thus
impact translation quality of neural machine translation (NMT) models. In this paper, we …
impact translation quality of neural machine translation (NMT) models. In this paper, we …
Neural machine translation with GRU-gated attention model
Neural machine translation (NMT) heavily relies on context vectors generated by an
attention network to predict target words. In practice, we observe that the context vectors for …
attention network to predict target words. In practice, we observe that the context vectors for …
Training deeper neural machine translation models with transparent attention
While current state-of-the-art NMT models, such as RNN seq2seq and Transformers,
possess a large number of parameters, they are still shallow in comparison to convolutional …
possess a large number of parameters, they are still shallow in comparison to convolutional …
Neural machine translation with deep attention
Deepening neural models has been proven very successful in improving the model's
capacity when solving complex learning tasks, such as the machine translation task …
capacity when solving complex learning tasks, such as the machine translation task …
Improving deep transformer with depth-scaled initialization and merged attention
The general trend in NLP is towards increasing model capacity and performance via deeper
neural networks. However, simply stacking more layers of the popular Transformer …
neural networks. However, simply stacking more layers of the popular Transformer …
Asynchronous bidirectional decoding for neural machine translation
The dominant neural machine translation (NMT) models apply unified attentional encoder-
decoder neural networks for translation. Traditionally, the NMT decoders adopt recurrent …
decoder neural networks for translation. Traditionally, the NMT decoders adopt recurrent …
Graph-to-tree neural networks for learning structured input-output translation with applications to semantic parsing and math word problem
The celebrated Seq2Seq technique and its numerous variants achieve excellent
performance on many tasks such as neural machine translation, semantic parsing, and math …
performance on many tasks such as neural machine translation, semantic parsing, and math …
Variational recurrent neural machine translation
Partially inspired by successful applications of variational recurrent neural networks, we
propose a novel variational recurrent neural machine translation (VRNMT) model in this …
propose a novel variational recurrent neural machine translation (VRNMT) model in this …
Regularizing neural machine translation by target-bidirectional agreement
Abstract Although Neural Machine Translation (NMT) has achieved remarkable progress in
the past several years, most NMT systems still suffer from a fundamental shortcoming as in …
the past several years, most NMT systems still suffer from a fundamental shortcoming as in …